Intelligent scheduling and order dispatching management method and system

Abstract

The invention discloses an intelligent scheduling and order dispatching management method and system, and relates to the technical field of intelligent scheduling, and the method comprises the steps: collecting original data, and carrying out the preprocessing; performing feature extraction on the preprocessed original data to obtain task priority related features and employee condition related features; based on historical data, constructing an intelligent scheduling model, inputting task priority related features into the intelligent scheduling model, calculating task priority scores, and performing task priority ranking according to the task priority scores; on the basis of task priority ranking and employee condition related characteristics, optimal matching personnel are automatically selected for task allocation; and monitoring execution condition data of the task in real time, and optimizing the intelligent scheduling model by utilizing the execution condition data. According to the method, the intelligent scheduling model is constructed, the health and skills of employees are considered, efficient and reasonable distribution is ensured, the model is optimized in real time, and the task execution quality and efficiency are improved.

Description

Technical Field

[0001] The present invention relates to the field of intelligent scheduling technology, and in particular to a method and system for intelligent scheduling and dispatch management. Background Art

[0002] With the continuous development of modern enterprises and the advancement of technology, the production and service industries are facing increasingly complex task management and scheduling problems. Traditional task allocation methods often rely on manual experience and judgment, lack scientificity and systematicness, and are difficult to cope with the growing business needs. In recent years, with the development of artificial intelligence technology, especially the application of machine learning and deep learning, intelligent scheduling and dispatch management systems have gradually become one of the important means to improve work efficiency and management level. Such systems usually collect and analyze various data to achieve intelligent allocation and scheduling of tasks, thereby improving production efficiency and customer satisfaction.

[0003] However, existing intelligent scheduling and dispatch management systems have certain limitations. First, most systems only focus on data features of a single dimension, such as the urgency of the task or the health of the equipment, while ignoring other important features in task priority assessment, resulting in inaccurate task allocation. Second, many systems fail to fully consider employee status information, especially employee health status and skill level, which directly affects the quality and efficiency of task execution. In addition, the existing systems have low adaptability in real-time monitoring of task execution status and dynamic adjustment of scheduling models, and are unable to respond to changes in task execution in a timely manner, which makes task allocation incomplete and unreasonable, and may lead to waste of resources or delay the completion of important tasks. Summary of the invention

[0004] In view of the above existing problems, the present invention is proposed.

[0005] Therefore, the present invention provides a method and system for intelligent scheduling and dispatch management to solve the problem that the prior art lacks consideration of task priority assessment and employee status.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0007] In the first aspect, an embodiment of the present invention provides a method for intelligent scheduling and dispatch management, which includes collecting raw data and preprocessing it; the raw data includes equipment operating status, employee status data and historical task data; extracting features from the preprocessed raw data to obtain task priority-related features and employee status-related features; building an intelligent scheduling model based on historical data, inputting task priority-related features into the intelligent scheduling model, calculating task priority scores, and sorting tasks according to the task priority scores; automatically selecting the best matching personnel for task assignment based on task priority sorting and employee status-related features; monitoring task execution status data in real time, and using the execution status data to optimize the intelligent scheduling model.

[0008] As a preferred solution of the method for intelligent scheduling and dispatching management of the present invention, the steps of collecting raw data and preprocessing are as follows:

[0009] Collect equipment operating status through sensors and / or monitoring systems on the equipment;

[0010] Obtain employee status data from the human resource management system, including employee skill levels and health indexes;

[0011] Collect historical task data from the ERP system, including task type, task completion time and executor;

[0012] The collected equipment operation status data, employee status data and historical task data are processed for outliers, missing values ​​and data structuring.

[0013] As a preferred solution of the method for intelligent scheduling and dispatch management of the present invention, the following specific steps are performed to extract features of the pre-processed raw data to obtain features related to task priority and features related to employee status:

[0014] The statistical method is used to extract the task priority related features from the pre-processed equipment operation status data and historical task data. The task priority related features include: equipment health index, task completion time and task urgency;

[0015] Data mining is used to extract employee status related features from the pre-processed employee status data. The employee status related features include: employee health index and skill level.

[0016] As a preferred solution of the method for intelligent scheduling and dispatch management of the present invention, wherein: based on historical data, an intelligent scheduling model is constructed, the task priority-related features are input into the intelligent scheduling model, and the task priority score is calculated. The specific steps are as follows:

[0017] Use LSTM neural network as the basic model and input historical data into the network through the input layer;

[0018] Inside the network, the LSTM unit processes historical data in a time series manner to capture the trends and patterns of historical data over time, and saves and updates the equipment health index, task completion time, and task urgency through the memory units and gating mechanisms in the hidden layer;

[0019] The model parameters are adjusted through the back-propagation algorithm and gradient descent method to minimize the loss function. Finally, the LSTM neural network is trained into an intelligent scheduling model that can predict the task priority score.

[0020] The task priority-related features are input into the intelligent scheduling model, and the nonlinear regression algorithm is used to predict the task priority score. The expression is:

[0021]

[0022] Among them, α represents the initial priority of the task, β is the task urgency coefficient, δ is the equipment status coefficient, and E j Indicates the urgency of task j, T j represents the completion time of task j, H j represents the device health index associated with task j, P j represents the priority score of task j.

[0023] As a preferred solution of the method for intelligent scheduling and dispatch management of the present invention, the specific steps of sorting the task priorities according to the task priority scores are as follows:

[0024] Create a file containing all tasks and their corresponding priority scores P j 's task list and initialize a task priority queue J;

[0025] Traverse each task j in the task list and compare each task j with the corresponding priority score P j Add to the task priority queue J;

[0026] Score the tasks in the task priority queue J according to the priority P j Sort in descending order.

[0027] As a preferred solution of the method for intelligent scheduling and dispatch management of the present invention, the following specific steps are taken to automatically select the best matching personnel for task assignment based on task priority sorting and employee status-related characteristics:

[0028] Obtain the latest employee workload and work time period from the ERP system; workload includes: the number of tasks and workload that the employee is currently responsible for;

[0029] Analyze the employee's availability level based on their latest workload and working time period. The expression is:

[0030]

[0031] Among them, k is the employee's workload coefficient, u is the impact coefficient of the employee's time to get off work, is the current workload of employee e, τ w is the upper threshold of the employee's workload, is the remaining time from the current time of the i-th employee e to the end of get off work time, Δt is the length of a standardized time period, is the current availability level of the i-th employee e, e i represents the i-th employee e, where i is the index variable;

[0032] Combining employee status-related features, task priority queues, and employee availability Calculate the task priority score P in the employee and task priority queue J j The highest task matching score is expressed as:

[0033]

[0034] Where j' represents the task with the highest priority score in the task priority queue J, η i represents the matching coefficient between the ith employee e and the task j' with the highest priority score, represents the health index of the i-th employee e, represents the skill level of the i-th employee e, P j' represents the priority score of the current highest priority task j', γ represents the influence coefficient of the difference between health status and skill level, λ is the influence coefficient of task priority, E j' represents the urgency of the task j' with the highest priority score, M(e i ,j') represents the matching score between the highest priority task j' and the i-th employee e;

[0035] According to the matching score M(e i , j'), compare all employees and assign the current highest priority task j' to the employee e with the highest matching score i As an executive;

[0036] When the task j' with the highest priority score in the task priority queue J is assigned, the next task j in the task priority queue J is automatically updated to the task j' with the highest priority score and assigned again until all tasks are assigned to the best matching personnel.

[0037] As a preferred solution of the method for intelligent scheduling and dispatch management of the present invention, the execution status data of the task is monitored in real time, and the intelligent scheduling model is optimized by using the execution status data. The specific steps are as follows:

[0038] During the task execution process, the execution status data of the task execution process is obtained from the monitoring system. The execution status data includes the equipment operation status, the actual completion time of the task and the feedback information of the executor;

[0039] The collected task execution status data is fed back to the intelligent scheduling model, the parameters of the intelligent scheduling model are updated, and the intelligent scheduling model is continuously optimized.

[0040] In a second aspect, the present invention provides a system for intelligent scheduling and dispatch management, including a data collection and preprocessing module, a feature extraction module, an intelligent scheduling module, a task allocation module, and an execution status monitoring and model optimization module;

[0041] Data collection and preprocessing module: used to collect and preprocess raw data; raw data includes equipment operation status, employee status data, and historical task data;

[0042] Feature extraction module: used to extract features from the preprocessed raw data to obtain features related to task priority and employee status;

[0043] Intelligent scheduling module: Based on historical data, build an intelligent scheduling model, input task priority-related features into the intelligent scheduling model, calculate task priority scores, and sort tasks according to the task priority scores;

[0044] Task assignment module: used to automatically select the best matching personnel for task assignment based on task priority sorting and employee status-related characteristics;

[0045] Execution status monitoring and model optimization module: used to monitor the execution status data of tasks in real time and use the execution status data to optimize the intelligent scheduling model.

[0046] In a third aspect, an embodiment of the present invention provides a computer device, comprising a memory and a processor, wherein the memory stores a computer program, wherein: when the computer program is executed by the processor, any step of the method of intelligent scheduling and dispatch management as described in the first aspect of the present invention is implemented.

[0047] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein: when the computer program is executed by a processor, it implements any step of the method of intelligent scheduling and dispatch management as described in the first aspect of the present invention.

[0048] The beneficial effects of the present invention are as follows: by comprehensively evaluating the characteristics of the original data, including the equipment operating status, employee status and historical task data, an intelligent scheduling model is constructed to achieve accurate prediction and reasonable allocation of task priorities. By fully considering the health status and skill level of employees, it is ensured that task allocation is not only efficient but also reasonable, thereby improving the quality and efficiency of task execution. Finally, by real-time monitoring of task execution status and dynamically optimizing the model, the accuracy and efficiency of task allocation are further improved, avoiding waste of resources and delays in important tasks. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0050] Figure 1 This is a flow chart of the method for intelligent scheduling and dispatch management in Example 1.

[0051] Figure 2 This is a flow chart of the intelligent scheduling and dispatch management system in Example 1. DETAILED DESCRIPTION

[0052] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the accompanying drawings.

[0053] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0054] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.

[0055] Example 1, reference Figure 1 and Figure 2, which is the first embodiment of the present invention, and provides a method for intelligent scheduling and dispatching management, comprising the following steps:

[0056] S1. Collect raw data and preprocess them.

[0057] Furthermore, the equipment operation status is collected through sensors and / or monitoring systems on the equipment; employee status data is obtained from the human resources management system, and the employee status data includes the employee's skill level and health index; historical task data is collected from the ERP system, and the historical task data includes the task type, task completion time and executor; outlier processing, missing value processing and data structuring are performed on the collected equipment operation status data, employee status data and historical task data.

[0058] The specific process of outlier processing is as follows: detect potential outliers through statistical analysis (such as calculating the mean and standard deviation) and visualization techniques (such as box plots); process the detected outliers by filling them with the median or directly removing them to ensure the consistency of data quality.

[0059] The specific process of missing value processing is: identify the location of missing values ​​through data cleaning tools or programming scripts; select appropriate processing strategies based on the number and distribution of missing values, such as deleting records with missing values ​​and using linear interpolation to fill missing values, to ensure the integrity and availability of the data set.

[0060] The specific process of data structuring is as follows: convert text or other unstructured data into structured data (such as tabular form) through data parsing technology; normalize the data to ensure data consistency and comparability, such as unified date format, unit conversion, etc.; finally, use database or data warehouse technology to organize and store structured data for subsequent data query and analysis.

[0061] S2. Perform feature extraction on the preprocessed raw data to obtain task priority related features and employee status related features.

[0062] Furthermore, a statistical method is used to extract task priority related features from the pre-processed equipment operation status data and historical task data. The task priority related features include: equipment health index, task completion time and task urgency.

[0063] It should be noted that the equipment health index is obtained by comprehensively analyzing the equipment's operating status data and maintenance records. The specific process is: collect the equipment's operating parameters, such as temperature, pressure, and vibration frequency, from the equipment's real-time monitoring system. Then, analyze the equipment's maintenance records, including the number of repairs, replacement parts records, and downtime, and convert these maintenance records into quantitative indicators. Then, set the corresponding weight according to the importance of each parameter to the equipment's health status. Finally, combine these standardized parameters through weighted summation to obtain the equipment's health index.

[0064] The urgency of a task is determined by analyzing the key attributes of the task. The specific process is: extracting information such as the completion time and deadline of the task from historical task data, which reflects the timeliness of the task. In addition, it is necessary to collect information such as the importance of the task and the urgency of customer needs. This information comes from customer feedback, the nature of the task, and the impact of the task on the business process. Then, these qualitative descriptions are quantified, such as by expert evaluation or by using certain scoring criteria to convert them into numerical values. Then, according to the degree of influence of these key attributes on the urgency of the task, the corresponding weights are set. Finally, these quantified information are combined through weighted summation to obtain the urgency of the task.

[0065] Data mining is used to extract employee status related features from the pre-processed employee status data. The employee status related features include: employee health index and skill level.

[0066] It should be noted that the employee health index is obtained by analyzing the health data of employees. First, physical examination records and sick leave records are collected from health records and standardized. Then, weights are set according to the importance of each health indicator, and finally, the employee health index is obtained through comprehensive evaluation.

[0067] The skill level of employees is determined by analyzing their skill data. First, skill-related information is collected from training records and personal performance evaluations and standardized. Then, weights are set based on the importance of each skill indicator. Finally, the skill level of the employee is obtained through comprehensive evaluation.

[0068] S3. Based on historical data, an intelligent scheduling model is constructed, and the task priority-related features are input into the intelligent scheduling model, the task priority score is calculated, and the task priority is sorted according to the task priority score.

[0069] Furthermore, using LSTM neural network as the basic model, historical data is input into the network through the input layer;

[0070] Within the network, the LSTM unit processes historical data in a time series manner, capturing the trends and patterns of historical data over time, and saves and updates the equipment health index, task completion time, and task urgency through the memory units and gating mechanisms in the hidden layer.

[0071] Historical data includes: equipment operation status data, employee status data and historical task data.

[0072] The model parameters are adjusted through the back-propagation algorithm and gradient descent method to minimize the loss function. Finally, the LSTM neural network is trained into an intelligent scheduling model that can predict task priority scores.

[0073] The task priority-related features are input into the intelligent scheduling model, and the nonlinear regression algorithm is used to predict the task priority score. The expression is:

[0074]

[0075] Among them, α represents the initial priority of the task, β is the task urgency coefficient, δ is the equipment status coefficient, and E j Indicates the urgency of task j, T j represents the completion time of task j, H j represents the device health index associated with task j, P j represents the priority score of task j; the urgency coefficient β represents the impact of task urgency on priority; the equipment status coefficient δ represents the impact of equipment health index on priority.

[0076] It should be noted that the task priority score P j First, the initial priority α of the task is used as the initial value; then, according to the task urgency E j Multiply it by the urgency coefficient β to reflect the urgency of the task; then calculate the time required to complete the task T j and equipment health index H j The ratio of the three parts is multiplied by the equipment status coefficient δ, which reflects the impact of the equipment health status on the task completion capability. The three parts are added and the reciprocal is taken to finally obtain the priority score P of task j. j .

[0077] Create a file containing all tasks and their corresponding priority scores P j 's task list and initialize a task priority queue J.

[0078] Traverse each task j in the task list and compare each task j with the corresponding priority score P j Add to the task priority queue J.

[0079] Score the tasks in the task priority queue J according to the priority P j Sort in descending order, that is, the higher the priority score, the higher the priority of the task.

[0080] It should also be noted that this process not only improves the accuracy of task priority prediction, but also predicts the task priority score through a nonlinear regression algorithm, ensuring the scientificity and rationality of the score. Creating a task priority queue and sorting the tasks in descending order of priority score helps the system automatically select the best matching personnel for task assignment, thereby improving the efficiency and quality of task processing and ensuring that high-priority tasks can be processed in a timely and effective manner.

[0081] S4. Automatically select the best matching personnel for task assignment based on task priority ranking and employee status-related characteristics.

[0082] Furthermore, the latest workload and work time period of the employees are obtained from the ERP system; the workload includes the number of tasks and workload that the employees are currently responsible for.

[0083] Analyze the employee's availability level based on their latest workload and working time period. The expression is:

[0084]

[0085] Among them, k is the employee's workload coefficient, u is the impact coefficient of the employee's time to get off work, is the current workload of employee e, τ w is the upper threshold of the employee's workload, is the remaining time from the current time of the i-th employee e to the end of get off work time, Δt is the length of a standardized time period, is the current availability level of the i-th employee e, e i represents the i-th employee e, where i is the index variable;

[0086] Combining employee status-related features, task priority queues, and employee availability Calculate the task priority score P in the employee and task priority queue J j The highest task matching score is expressed as:

[0087]

[0088] Where j' represents the task with the highest priority score in the task priority queue J, η i represents the matching coefficient between the ith employee e and the task j' with the highest priority score, represents the health index of the i-th employee e, represents the skill level of the i-th employee e, P j' represents the priority score of the current highest priority task j', γ represents the influence coefficient of the difference between health status and skill level, λ is the influence coefficient of task priority, E j' represents the urgency of the task j' with the highest priority score, M(e i ,j') represents the matching score between the highest priority task j' and the i-th employee e.

[0089] It should be noted that the matching score M(e i , j') is calculated by the following process: First, the matching coefficient η between the i-th employee e and the task j' with the highest priority score is calculated. i As the basic value; then, according to the health index of the i-th employee e ( and skill level The difference is multiplied by the influence coefficient γ of the difference in health status and skill level to reflect the impact of employee health and skills on matching; then, the priority score P of the task j' with the highest priority score is j' With urgency level E j' Combine the impact coefficient λ of task priority and the urgency coefficient β to calculate and take the cube root to reflect the impact of task priority and urgency on matching degree; finally, multiply the results of the above two parts and multiply them by the employee e i Availability Get the matching score M(e) between the i-th employee and the task j' with the highest priority score i ,j'). This process ensures that the employee's health, skill level, task priority and urgency, and employee availability are taken into account to arrive at a reasonable match score.

[0090] According to the matching score M(e i , j'), compare all employees and assign the current highest priority task j' to the employee e with the highest matching score i As an executive.

[0091] When the task j' with the highest priority score in the task priority queue J is assigned, the next task j in the task priority queue J is automatically updated to the task j' with the highest priority score and assigned again until all tasks are assigned to the best matching personnel.

[0092] It should also be noted that this process takes into account the health status, skill level, current workload, and priority and urgency of the task, so that the system can automatically select the best matching personnel for task allocation. This not only improves the efficiency and quality of task processing, but also ensures that high-priority tasks can be processed in a timely and effective manner, while also taking into account the availability and workload of employees, achieving the optimal allocation of resources.

[0093] S5. Monitor the execution status data of the task in real time and use the execution status data to optimize the intelligent scheduling model.

[0094] Furthermore, during the task execution process, the execution status data of the task execution process is obtained from the monitoring system, and the execution status data includes the equipment operation status, the actual completion time of the task and the feedback information of the executor.

[0095] The collected task execution status data is fed back to the intelligent scheduling model, the parameters of the intelligent scheduling model are updated, and the intelligent scheduling model is continuously optimized to improve the accuracy and efficiency of task allocation.

[0096] It should also be noted that during the task execution process, the system collects task execution status data in real time, uses the cross-entropy loss function to measure the accuracy of the intelligent scheduling model's predictions, and uses the gradient descent method to update the intelligent scheduling model parameters until the intelligent scheduling model performance reaches the optimal level or meets the predetermined number of iterations, thereby achieving continuous optimization of the intelligent scheduling model; with the execution of more tasks and the accumulation of data, the intelligent scheduling model will be able to better adapt to changes in the actual working environment, improve the accuracy and efficiency of task allocation, and ultimately achieve more accurate task priority sorting and personnel matching, thereby significantly improving the overall operating efficiency of the system.

[0097] This embodiment also provides a system for intelligent scheduling and dispatch management, including: a data collection and preprocessing module, a feature extraction module, an intelligent scheduling module, a task allocation module, and an execution status monitoring and model optimization module;

[0098] Data collection and preprocessing module: used to collect and preprocess raw data; raw data includes equipment operation status, employee status data, and historical task data;

[0099] Feature extraction module: used to extract features from the preprocessed raw data to obtain features related to task priority and employee status;

[0100] Intelligent scheduling module: Based on historical data, build an intelligent scheduling model, input task priority-related features into the intelligent scheduling model, calculate task priority scores, and sort tasks according to the task priority scores;

[0101] Task assignment module: used to automatically select the best matching personnel for task assignment based on task priority sorting and employee status-related characteristics;

[0102] Execution status monitoring and model optimization module: used to monitor the execution status data of tasks in real time and use the execution status data to optimize the intelligent scheduling model.

[0103] This embodiment also provides a computer device suitable for the method of intelligent scheduling and dispatch management, including: a memory and a processor; the memory is used to store computer executable instructions, and the processor is used to execute computer executable instructions to implement the method of intelligent scheduling and dispatch management proposed in the above embodiment.

[0104] The computer device may be a terminal, and the computer device includes a processor, a memory, a communication interface, a display screen and an input device connected via a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be achieved through WIFI, an operator network, NFC (near field communication) or other technologies. The display screen of the computer device may be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device may be a touch layer covering the display screen, or a key, trackball or touchpad provided on the housing of the computer device, or an external keyboard, touchpad or mouse, etc.

[0105] The present embodiment also provides a storage medium on which a computer program is stored. When the program is executed by the processor, the method for realizing intelligent scheduling and dispatch management as proposed in the above embodiment is implemented; the storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (Static Random Access Memory, referred to as SRAM), electrically erasable programmable read-only memory (Electrically Erasable Programmable Read-Only Memory, referred to as EEPROM), erasable programmable read-only memory (Erasable Programmable Read Only Memory, referred to as EPROM), programmable read-only memory (Programmable Red-Only Memory, referred to as PROM), read-only memory (Read-Only Memory, referred to as ROM), magnetic storage, flash memory, magnetic disk or optical disk.

[0106] In summary, the present invention builds an intelligent scheduling model through comprehensive evaluation of raw data features, including equipment operating status, employee status, and historical task data, to achieve accurate prediction and reasonable allocation of task priorities. By fully considering the health status and skill level of employees, it ensures that task allocation is not only efficient but also reasonable, thereby improving the quality and efficiency of task execution. Finally, by real-time monitoring of task execution status and dynamically optimizing the model, the accuracy and efficiency of task allocation are further improved, avoiding waste of resources and delays in important tasks.

[0107] Example 2, referring to Table 1, is the second example of the present invention. To further verify the technical solution of the present invention, experimental simulation data of the intelligent scheduling and dispatch management method are provided.

[0108] The present invention was tested in a manufacturing company. The company has a variety of equipment on the production line and about 100 employees. During the test, equipment operation status data was collected from the monitoring system, employee status data was obtained from the human resources management system, and historical task data was collected from the ERP system.

[0109] First, the equipment operation status data was collected through the sensors and monitoring systems on the equipment, and data such as employees' skill levels and health indexes were obtained from the human resources management system. At the same time, historical task data was collected from the ERP system, and necessary preprocessing was performed to ensure data quality.

[0110] Secondly, statistical methods and data mining techniques were used to extract task priority-related features from equipment operation status data and historical task data. The LSTM model was used for training, and the model parameters were adjusted through the back-propagation algorithm and gradient descent method. Finally, an intelligent scheduling model that can predict task priority scores was formed.

[0111] Next, a task priority queue was created and sorted in descending order based on the priority score, and the highest priority tasks were assigned to the employees with the highest match scores, taking into account the employees’ availability level and match scores.

[0112] Finally, during the task execution process, execution status data was collected from the monitoring system and fed back to the intelligent scheduling model. By updating the model parameters, the model performance was continuously optimized, thereby improving the accuracy and efficiency of task allocation.

[0113] The details are shown in Table 1 below:

[0114] Table 1 Task priority rating table

[0115]

[0116]

[0117] From the table above, we can see that among tasks A to D, task C has the highest task priority score (0.0028) due to its higher urgency (0.9) and lower equipment health index (78). In contrast, although task D has a lower urgency (0.7), its task priority score (0.0016) is relatively low due to its higher equipment health index (95) and shorter task completion time (6 hours).

[0118] After Task C is determined as the highest priority task, the system combines the employee's availability level and matching score to calculate the matching score of each employee with Task C. For example, employee E1's health index is 90, skill level is 85, availability level is 0.9, matching coefficient is 0.8, priority score of Task C is 0.0028, urgency is 0.9, and the matching score of employee E1 is 0.85. Similarly, the matching scores of other employees are calculated, and Task C is assigned to employee E1 with the highest matching score. Subsequently, Task A, Task B, and Task D are assigned in turn according to their priority scores to ensure that each task is performed by the most suitable employee, thereby improving the accuracy and efficiency of task assignment and ensuring the quality and timeliness of task execution.

[0119] The present invention can accurately reflect the priority of tasks by comprehensively evaluating the equipment health index, task completion time and task urgency. Compared with the existing method of simply sorting tasks according to task completion time or urgency, the present invention can comprehensively consider the equipment status and task characteristics, so that the task allocation is more reasonable and efficient. In particular, for tasks with low equipment health index, the present invention can identify and prioritize them earlier, avoiding task delays caused by equipment failure.

[0120] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A method for intelligent scheduling and dispatching management, characterized by: include, Collect and pre-process raw data; the raw data includes equipment operation status, employee status data, and historical task data; Perform feature extraction on the preprocessed raw data to obtain features related to task priority and employee status; Based on historical data, an intelligent scheduling model is built, and the task priority-related features are input into the intelligent scheduling model to calculate the task priority score, and the task priority is sorted according to the task priority score; Automatically select the best matching personnel for task assignment based on task priority ranking and employee status-related characteristics; Monitor task execution status data in real time and use the execution status data to optimize the intelligent scheduling model.

2. The method of intelligent scheduling and dispatching management according to claim 1, characterized in that: The specific steps of collecting raw data and preprocessing are as follows: Collect equipment operating status through sensors and / or monitoring systems on the equipment; Obtain employee status data from the human resource management system, including employee skill levels and health indexes; Collect historical task data from the ERP system, including task type, task completion time and executor; The collected equipment operation status data, employee status data and historical task data are processed for outliers, missing values ​​and data structuring.

3. The method of intelligent scheduling and dispatching management according to claim 2, characterized in that: The feature extraction of the preprocessed raw data to obtain the task priority related features and employee status related features is performed in the following specific steps: The statistical method is used to extract the task priority related features from the pre-processed equipment operation status data and historical task data. The task priority related features include: equipment health index, task completion time and task urgency; Data mining is used to extract employee status related features from the pre-processed employee status data. The employee status related features include: employee health index and skill level.

4. The method of intelligent scheduling and dispatching management as claimed in claim 3, characterized in that: Based on the historical data, an intelligent scheduling model is constructed, the task priority-related features are input into the intelligent scheduling model, and the task priority score is calculated. The specific steps are as follows: Use LSTM neural network as the basic model and input historical data into the network through the input layer; Inside the network, the LSTM unit processes historical data in a time series manner to capture the trends and patterns of historical data over time, and saves and updates the equipment health index, task completion time, and task urgency through the memory units and gating mechanisms in the hidden layer; The model parameters are adjusted through the back-propagation algorithm and gradient descent method to minimize the loss function. Finally, the LSTM neural network is trained into an intelligent scheduling model that can predict the task priority score. The task priority-related features are input into the intelligent scheduling model, and the nonlinear regression algorithm is used to predict the task priority score. The expression is: Among them, α represents the initial priority of the task, β is the task urgency coefficient, δ is the equipment status coefficient, and E j represents the urgency of task j, T j represents the completion time of task j, H j represents the device health index associated with task j, P j represents the priority score of task j.

5. The method of intelligent scheduling and dispatching management as claimed in claim 4, characterized in that: The specific steps of sorting the task priorities according to the task priority scores are as follows: Create a file containing all tasks and their corresponding priority scores P j 's task list and initialize a task priority queue J; Traverse each task j in the task list and compare each task j with the corresponding priority score P j Add to the task priority queue J; Score the tasks in the task priority queue J according to the priority P j Sort in descending order.

6. The method of intelligent scheduling and dispatching management according to claim 5, characterized in that: The specific steps of automatically selecting the best matching personnel for task allocation based on task priority sorting and employee status-related characteristics are as follows: Obtain the latest employee workload and work time period from the ERP system; workload includes: the number of tasks and workload that the employee is currently responsible for; Analyze the employee's availability level based on their latest workload and working time period. The expression is: Among them, k is the employee's workload coefficient, u is the impact coefficient of the employee's time to get off work, is the current workload of the i-th employee e, τ w is the upper threshold of the employee's workload, is the remaining time from the current time of the i-th employee e to the end of get off work time, Δt is the length of a standardized time period, is the current availability level of the i-th employee e, e i represents the i-th employee e, where i is the index variable; Combining employee status-related features, task priority queues, and employee availability Calculate the task priority score P in the employee and task priority queue J j The highest task matching score is expressed as: Where j' represents the task with the highest priority score in the task priority queue J, η i represents the matching coefficient between the ith employee e and the task j' with the highest priority score, represents the health index of the i-th employee e, represents the skill level of the i-th employee e, P j' represents the priority score of the current highest priority task j', γ represents the influence coefficient of the difference between health status and skill level, λ is the influence coefficient of task priority, E j' represents the urgency of the task j' with the highest priority score, M(e i ,j') represents the matching score between the highest priority task j' and the i-th employee e; According to the matching score M(e i , j'), compare all employees and assign the current highest priority task j' to the employee e with the highest matching score i As an executive; When the task j' with the highest priority score in the task priority queue J is assigned, the next task j in the task priority queue J is automatically updated to the task j' with the highest priority score and assigned again until all tasks are assigned to the best matching personnel.

7. The method of intelligent scheduling and dispatching management according to claim 6, characterized in that: The execution status data of the task is monitored in real time, and the intelligent scheduling model is optimized using the execution status data. The specific steps are as follows: During the task execution process, the execution status data of the task execution process is obtained from the monitoring system. The execution status data includes the equipment operation status, the actual completion time of the task and the feedback information of the executor; The collected task execution status data is fed back to the intelligent scheduling model, the parameters of the intelligent scheduling model are updated, and the intelligent scheduling model is continuously optimized.

8. A system for intelligent scheduling and dispatch management, characterized by: include, Data collection and preprocessing module, feature extraction module, intelligent scheduling module, task allocation module and execution status monitoring and model optimization module; Data collection and preprocessing module: used to collect and preprocess raw data; raw data includes equipment operation status, employee status data, and historical task data; Feature extraction module: used to extract features from the preprocessed raw data to obtain features related to task priority and employee status; Intelligent scheduling module: Based on historical data, build an intelligent scheduling model, input task priority-related features into the intelligent scheduling model, calculate task priority scores, and sort tasks according to the task priority scores; Task assignment module: used to automatically select the best matching personnel for task assignment based on task priority sorting and employee status-related characteristics; Execution status monitoring and model optimization module: used to monitor the execution status data of tasks in real time and use the execution status data to optimize the intelligent scheduling model.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method for intelligent scheduling and dispatch management described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method for intelligent scheduling and dispatch management described in any one of claims 1 to 7 are implemented.

Images